Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1069 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.3298. Min Act: -0.0000

Data Index: 759555 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.3087. Min Act: -0.0000

Data Index: 599945 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.3086. Min Act: -0.0000

Data Index: 227891 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2634. Min Act: -0.0000

Data Index: 211896 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1084797 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2607. Min Act: -0.0000

Data Index: 123484 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2662. Min Act: -0.0000

Data Index: 397158 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1356610 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2392. Min Act: -0.0000

Data Index: 807935 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2408. Min Act: -0.0000

Data Index: 798255 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2390. Min Act: -0.0000

Data Index: 146035 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2242. Min Act: -0.0000

Data Index: 5923 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2182. Min Act: -0.0000

Data Index: 664554 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1151320 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2143. Min Act: -0.0000

Data Index: 958058 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2303. Min Act: -0.0000

Data Index: 620675 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2267. Min Act: -0.0000

Data Index: 1200542 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2321. Min Act: -0.0000

Data Index: 450259 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2091. Min Act: -0.0000

Data Index: 696407 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1311908 (C4 (Web Text))

Max Activating Token Index: 332